> For the complete documentation index, see [llms.txt](https://icij.gitbook.io/datashare/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://icij.gitbook.io/datashare/local-mode/transcribe-audio-and-video.md).

# Transcribe audio and video

This page explains how to set up ASR, install the ASR plugin, and transcribe audio and video documents on your computer.

{% hint style="info" %}
The ASR plugin automatically transcribes audio and video documents into text using speech recognition models. Processing stays within Datashare. No data is sent to third parties.
{% endhint %}

## How it works

The ASR feature relies on three components:

* The **ASR plugin** (`datashare-plugin-asr`) adds the transcription interface, including language and model selectors.
* The **ASR extension** (`datashare-extension-asr`) exposes the ASR API and submits transcription workflows to Temporal.
* The **ASR workers** (`datashare-python`) preprocess audio, run model inference, and index results.

All three components must be installed and running.

## Prerequisites

### Datashare version

Use Datashare version `21.0.0` or later.

### Temporal

The ASR workers use [Temporal](https://temporal.io/) for task orchestration. Run a Temporal server that Datashare and every worker can reach. Start Datashare with:

```
--batchQueueType TEMPORAL --messageBusAddress temporal:7233 --taskRoutingStrategy GROUP
```

### Index your documents

Before transcribing, add your audio and video files through the **Documents** task. Wait until indexing finishes.

### Supported formats

The ASR plugin supports the following audio and video formats:

| Audio        | Video |
| ------------ | ----- |
| AAC          | MP4   |
| AIFF         | MPEG  |
| MP4 (audio)  | MOV   |
| MPEG (audio) |       |
| OGG          |       |
| WAV          |       |

### Next steps

1. [Install ASR plugin](/datashare/local-mode/transcribe-audio-and-video/install-asr-plugin.md).
2. [Transcribe documents](/datashare/local-mode/transcribe-audio-and-video/transcribe-documents.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://icij.gitbook.io/datashare/local-mode/transcribe-audio-and-video.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.